CN113010817B - Content validity period adjusting method, device, server and storage medium - Google Patents
Content validity period adjusting method, device, server and storage medium Download PDFInfo
- Publication number
- CN113010817B CN113010817B CN201911312413.2A CN201911312413A CN113010817B CN 113010817 B CN113010817 B CN 113010817B CN 201911312413 A CN201911312413 A CN 201911312413A CN 113010817 B CN113010817 B CN 113010817B
- Authority
- CN
- China
- Prior art keywords
- target content
- period
- contribution value
- content
- time
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 36
- 230000015654 memory Effects 0.000 claims description 11
- 238000004904 shortening Methods 0.000 claims description 10
- 238000012163 sequencing technique Methods 0.000 claims 2
- 238000010586 diagram Methods 0.000 description 23
- 230000000694 effects Effects 0.000 description 14
- 238000002474 experimental method Methods 0.000 description 14
- 230000002035 prolonged effect Effects 0.000 description 9
- 238000012937 correction Methods 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000008092 positive effect Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/957—Browsing optimisation, e.g. caching or content distillation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/958—Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The application discloses a method and a device for adjusting a content validity period, a server and a storage medium, and belongs to the technical field of networks. The method comprises the following steps: acquiring the contribution value of target content in a plurality of first time periods according to feedback data of the target content in the first time periods; when the online time of the target content reaches the first effective period, determining a contribution value trend of the target content according to the contribution values of the target content in the plurality of first time periods; and adjusting the first validity period of the target content according to the contribution value trend of the target content. According to the method and the device, the validity period of the content is adjusted according to the contribution value trend, the flexibility of the validity period setting is improved, and the contribution value of the content is considered in the adjustment of the validity period and is determined according to the feedback data, so that the validity period is high in accuracy.
Description
Technical Field
The present application relates to the field of network technologies, and in particular, to a method and apparatus for adjusting a content validity period, a server, and a storage medium.
Background
With the development of network technology, more and more users browse contents on the network, and the contents have a certain validity period, and the validity period determines the time for exposing the contents to the users, so that how to set the validity period of the contents is important.
The related art sets the validity period of the content according to the content classification, for example, the graphics context can be classified into more than ten categories of entertainment, game, cartoon, weather, financial and the like, and then different validity periods are set for the content according to different categories, for example, the "weather" category is 24 hours validity period, and the "game" category is 72 hours validity period. For any content, the content is set to expire immediately after the expiration date of the content is reached, and the content will no longer be exposed to the user.
The technology sets the validity period of the content according to the content classification, and immediately expires the content when the validity period is reached, so that the validity period is not set flexibly and has poor accuracy.
Disclosure of Invention
The embodiment of the application provides a method, a device, a server and a storage medium for adjusting the validity period of content, which can solve the problems of inflexible setting of the validity period and poor accuracy in the related technology. The technical scheme is as follows:
In one aspect, a method for adjusting a content validity period is provided, the method comprising:
Acquiring the contribution value of target content in a plurality of first time periods according to feedback data of the target content in the first time periods;
When the online time of the target content reaches the first effective period, determining a contribution value trend of the target content according to the contribution values of the target content in the plurality of first time periods;
And adjusting the first validity period of the target content according to the contribution value trend of the target content.
In one possible implementation manner, the adjusting the first validity period of the target content according to the contribution value trend of the target content includes:
And when the contribution value trend of the target content is that the target content is currently in a low-camouflage period for a long time, determining that the first effective period of the target content is immediately expired.
In one possible implementation manner, the determining the contribution value trend of the target content according to the currently acquired contribution value of the target content and the historically acquired contribution value of the target content includes:
Obtaining a percentile of a plurality of contribution values of the target content, the plurality of contribution values including the currently obtained contribution value of the target content and the historically obtained contribution value of the target content;
And when the acquired target number of the plurality of contribution values, the time of which is closest to the current time, is smaller than or equal to the percentile, determining that the contribution value trend of the target content is that the target content is in the low-camouflage period for a long time.
In one possible implementation manner, after the obtaining the percentile of the plurality of contribution values of the target content, the method further includes:
And when the contribution value of the currently acquired target content is larger than the percentile, determining that the contribution value trend of the target content is that the target content is currently in a prosperity period.
In one aspect, there is provided an apparatus for adjusting a content validity period, the apparatus comprising:
The acquisition module is used for acquiring the contribution value of the target content in a plurality of first time periods according to the feedback data of the target content in the first time periods;
the determining module is used for determining a contribution value trend of the target content according to the contribution values of the target content in the plurality of first time periods when the online time length of the target content reaches the first effective period;
and the adjusting module is used for adjusting the first validity period of the target content according to the contribution value trend of the target content.
In one possible implementation, the determining module is configured to:
obtaining percentiles of contribution values of the target content in the first time periods;
And when the contribution value of the target content in one first time period closest to the current time in the first time periods is larger than the percentile, determining that the contribution value trend of the target content is the current prosperity of the target content.
In one possible implementation, the determining module is configured to:
And when the contribution value of the target content in the target number of first time periods closest to the current time in the first time periods is smaller than or equal to the percentile, determining that the contribution value trend of the target content is that the target content is in the low-camouflage period for a long time.
In one possible implementation, the adjusting module is configured to:
And when the contribution value trend of the target content is that the target content is currently in a prosperous period, prolonging the first validity period of the target content to be a second validity period.
In one possible implementation, the adjusting module is configured to:
And when the contribution value trend of the target content is that the target content is currently in a low-camouflage period for a long time, determining that the first effective period of the target content is immediately expired.
In one possible implementation manner, the obtaining module is further configured to obtain, at intervals of a second time period, a contribution value of the target content in the second time period according to feedback data of the target content in the second time period;
the determining module is further used for determining a contribution value trend of the target content according to the currently acquired contribution value of the target content and the historically acquired contribution value of the target content;
the adjustment module is further configured to adjust the second validity period of the target content according to a contribution value trend of the target content.
In one possible implementation, the determining module is configured to:
Obtaining a percentile of a plurality of contribution values of the target content, the plurality of contribution values including the currently obtained contribution value of the target content and the historically obtained contribution value of the target content;
And when the acquired target number of the plurality of contribution values, the time of which is closest to the current time, is smaller than or equal to the percentile, determining that the contribution value trend of the target content is that the target content is in the low-camouflage period for a long time.
In one possible implementation, the determining module is configured to:
And when the contribution value of the currently acquired target content is larger than the percentile, determining that the contribution value trend of the target content is that the target content is currently in a prosperity period.
In one possible implementation, the adjusting module is configured to:
and shortening the second effective period of the target content to be immediately expired when the contribution value trend of the target content is that the target content is currently in a low-camouflage period for a long time.
In one possible implementation, the adjusting module is configured to:
and when the contribution value trend of the target content is that the target content is currently in a prosperous period and the online time of the target content reaches the second effective period, prolonging the second effective period of the target content to be a third effective period.
In one aspect, a server is provided, the server including a processor and a memory, the memory storing at least one piece of program code, the at least one piece of program code being loaded and executed by the processor to implement the method for adjusting the validity period of content.
In one aspect, a computer readable storage medium having at least one program code stored therein is provided, the at least one program code loaded and executed by a processor to implement the above-described method of adjusting a validity period of content.
The technical scheme provided by the embodiment of the application has the beneficial effects that at least:
By determining the contribution value of the content in a plurality of time periods according to the feedback data of the content in the plurality of time periods of the original validity period, the content is not directly expired when the original validity period is reached, but the validity period of the content is adjusted according to the trend of the contribution value, so that the flexibility of the validity period setting is improved, and the contribution value of the content is determined according to the feedback data due to the fact that the validity period is adjusted.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic diagram of an information flow provided by an embodiment of the present application;
FIG. 2 is a schematic diagram of an implementation environment of a method for adjusting a content validity period according to an embodiment of the present application;
FIG. 3 is a flowchart of a method for adjusting a content validity period according to an embodiment of the present application;
FIG. 4 is a schematic illustration of a system according to an embodiment of the present application that is in a latent period for a predetermined period of validity;
FIG. 5 is a schematic diagram of an embodiment of the present application providing a decay period that has been set when an expiration date expires;
FIG. 6 is a schematic illustration of an embodiment of the present application providing an initial expiration date still in a prosperous period;
FIG. 7 is a schematic diagram of a phase division provided by an embodiment of the present application;
FIG. 8 is a schematic diagram of a validity period calculation according to an embodiment of the present application;
FIG. 9 is a schematic diagram of an experimental effect of dynamically prolonging the validity period according to an embodiment of the present application;
FIG. 10 is a schematic diagram of an experimental effect of dynamically prolonging the validity period according to an embodiment of the present application;
FIG. 11 is a schematic diagram of an experimental effect of dynamically shortening the validity period according to an embodiment of the present application;
FIG. 12 is a schematic diagram of an experimental effect of dynamically shortening the validity period according to an embodiment of the present application;
fig. 13 is a schematic structural diagram of a device for adjusting the validity period of content according to an embodiment of the present application;
fig. 14 is a schematic structural diagram of a server 1400 according to an embodiment of the present application.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present application more apparent, the embodiments of the present application will be described in further detail with reference to the accompanying drawings.
Before explaining the embodiments of the present disclosure in detail, some key terms related to the embodiments of the present disclosure are explained.
Information flow: a content stream that can be scrolled through. Referring to fig. 1, fig. 1 is a schematic diagram of an information flow provided in an embodiment of the present application, and as shown in fig. 1, these contents may appear in sections that are similar in appearance and are displayed next to each other.
The content is as follows: the title and one to three cover images are displayed in the information flow, the user is guided to click into the text, and the text can be composed of characters, pictures and videos.
Percentile: statistical terms if a set of data is ordered from small to large and a corresponding cumulative percentile is calculated, the value of the data corresponding to a percentile is referred to as the percentile of that percentile. Can be expressed as: a set of n observations is arranged in numerical size. For example, a value at the p% position is referred to as a p% quantile. Wherein n and p are natural numbers.
Fig. 2 is a schematic diagram of an implementation environment of a method for adjusting a content validity period according to an embodiment of the present application, referring to fig. 2, the implementation environment may include:
At least one server 201 and at least one terminal 202. Wherein the server 201 is configured to provide information flow services to the terminal 202, and in particular, the server 201 may provide services to the terminal through an application installed by the terminal 202. The terminal 202 is used to run an application provided by the server 201 and realize various functions based on the application. In addition, the server 201 may also be configured with at least one database, such as a content database, a user database, and the like. The content database is used for storing various data related to the content, and the user database is used for storing personal data such as a user name, a password, a user relationship chain and the like of the user served by the server 201.
Fig. 3 is a flowchart of a method for adjusting a content validity period according to an embodiment of the present application. The method is performed by a server, see fig. 3, and may include:
301. And acquiring the contribution value of the target content in a plurality of first time periods according to the feedback data of the target content in the first time periods contained in the first validity period.
The target content can be any content on the content platform, and the server can adjust the validity period of each content by adopting the technical scheme provided by the embodiment of the application for each content. The first validity period may be a predetermined validity period, such as 72 hours, and the duration of the first time period may be a target duration, such as 1 hour. The feedback data refers to feedback data of the target content, such as clicking, commenting, praying, forwarding, collecting and the like, of the target content by the user after the target content is online. The contribution value refers to the value that the target content contributes to the platform.
After the target content is online, the server acquires feedback data of the target content in each first time period contained in the first validity period, and acquires the contribution value of the target content in each first time period according to the feedback data in each first time period. For example, before the online time of the target content reaches the first validity period, the server may acquire feedback data of the target content in the first period every other first period, and acquire a contribution value of the target content in the first period according to the feedback data in the first period. The contribution value may be calculated according to a contribution value algorithm, for example, the contribution value may be a reading amount, and the contribution value algorithm may be an algorithm for calculating the reading amount.
302. And when the online time of the target content reaches the first effective period, determining the contribution value trend of the target content according to the contribution values of the target content in the first time periods.
The server can determine the online time of the target content according to the current time and the online time of the target content, judge whether the online time of the target content reaches the first validity period, and determine the contribution value trend of the target content if the online time of the target content reaches the first validity period.
In one possible implementation manner, the determining the contribution value trend of the target content according to the contribution values of the target content in the first time periods includes the following steps a1 to a3:
step a1, obtaining percentiles of contribution values of the target content in the first time periods.
The percentile may be a 20% quantile, and the server may rank the contribution values of the target content from small to large in the first time periods, where 20% quantile refers to the contribution value at 20% position, for example, the ranking of the contribution values is 12345, and 20% quantile is 1.
And a2, when the contribution value of the target content in one first time period closest to the current time in the first time periods is larger than the percentile, determining that the contribution value trend of the target content is the current prosperity of the target content.
The plurality of first time periods have time sequence, the server can compare the contribution value of the target content in one first time period closest to the current time with the percentile, and if the contribution value is larger than the percentile, the contribution value trend of the target content can be determined as the current prosperity of the target content.
And a3, when the contribution value of the target content in the target number of the first time periods closest to the current time in the plurality of first time periods is smaller than or equal to the percentile, determining that the contribution value trend of the target content is that the target content is in the low-camouflage period for a long time.
The low-prizing period includes a latency period and a decay period, the latency period means that the contribution value is low all the time and does not enter the prosperity period, and the decay period means that the contribution value gradually decreases with the time after entering the prosperity period and does not enter the prosperity period again.
The server may determine, from the plurality of first time periods, a target number of first time periods closest to the current time, compare the contribution values of the target number of first time periods with the percentile obtained in step a1, respectively, and if both the contribution values are greater than the percentile, determine that the trend of the contribution values of the target content is that the target content is currently in the low-vague period for a long time.
It should be noted that, in addition to determining that the target content is currently in the prosperous period or has been in the low-priced period for a long time when the online time period reaches the first validity period, the server may determine that the target content is in the prosperous period or the low-priced period in each first period of the first validity period according to the contribution value of the target content in each first period of the plurality of first periods, for example, for each first period of the plurality of first periods, when the contribution value of the target content in the first period is greater than the percentile obtained in the step a1, the server may determine that the target content is in the prosperous period in the first period, and when the contribution value of the target content in the first period is less than or equal to the percentile obtained in the step a1, the server may determine that the target content is in the declining period in the first period.
303. When the contribution value trend of the target content is that the target content is currently in the low-vage period for a long time, the first effective period of the target content is determined to be immediately expired.
When it is determined, via step 302, that the target content is currently in the low-vage period for a long time, the server may immediately expire the target content, no exposure traffic is allocated to the target content, and the target content is no longer exposed to the user.
304. And when the contribution value trend of the target content is that the target content is currently in a prosperous period, prolonging the first validity period of the target content to be a second validity period.
When it is determined, via step 302, that the target content is currently in a prosperous period, the server may extend the original validity period of the target content, such as extending the first validity period to a second validity period. For example, the first validity period may be 72 hours and the second validity period may be 96 hours, i.e. extended by 24 hours.
Steps 303 and 304 are two possible implementations of adjusting the first validity period of the target content according to the contribution value trend of the target content. When the set effective period of the target content is reached, the contribution value trend of the target content is determined, so that the target content is known to be in the prosperous period or in the low-priced period for a long time, the effective period of the target content can be prolonged in time when the target content is in the prosperous period, and the target content can be expired in time when the target content is in the low-priced period for a long time.
305. And acquiring the contribution value of the target content in the second time period according to the feedback data of the target content in the second time period every second time period.
The duration of the second time period may be the same as the duration of the first time period, e.g., the duration of the second time period is also the target duration, e.g., 1h.
Before the online time of the target content reaches the second validity period after the extension, the server may acquire feedback data of the target content in the second time period every second time period, so as to acquire a contribution value of the target content in the second time period. The manner of obtaining the contribution value is the same as that of step 301, and will not be described again.
306. And determining the contribution value trend of the target content according to the contribution value of the target content acquired currently and the contribution value of the target content acquired historically.
After the server obtains the contribution value of the target content in the current time period, the contribution value trend of the target content can be determined according to the contribution value of the target content obtained in the current time period and the contribution value of the target content obtained in the historical time period before the current time period.
In one possible implementation manner, the determining the contribution value trend of the target content according to the currently acquired contribution value of the target content and the historically acquired contribution value of the target content includes the following steps b1 to b3:
Step b1, obtaining percentiles of a plurality of contribution values of the target content, wherein the plurality of contribution values comprise the contribution value of the currently obtained target content and the contribution value of the historically obtained target content.
Wherein, the percentile may be a 20% quantile, and the server may rank the plurality of contribution values from small to large, and the 20% quantile is the contribution value at the 20% position.
And b2, when the contribution value of the currently acquired target content is larger than the percentile, determining that the contribution value trend of the target content is that the target content is currently in a prosperous period.
The server may compare the contribution value of the target content to the percentile for the current time period and if greater than the percentile, may determine that the trend in the contribution value of the target content is currently in the prosperous period.
And b3, when the obtained number of the contribution values of the target number, the time of which is closest to the current time, in the plurality of contribution values is smaller than or equal to the percentile, determining that the trend of the contribution values of the target content is that the target content is in the low-camouflage period for a long time.
The server can determine the target number of contribution values with the time closest to the current time from the plurality of contribution values, compare the target number of contribution values with the percentile obtained in the step b1 respectively, and if the target number of contribution values are larger than the percentile, determine that the trend of the contribution values of the target content is that the target content is in the low-camouflage period for a long time.
307. Shortening the second validity period of the target content to be immediately expired when the contribution value trend of the target content is that the target content is currently in the low-vage period for a long time.
When it is determined by step 306 that the target content is currently in the low-profile period for a long period of time, indicating that the extended second validity period is too long, the server may immediately expire the target content without waiting until the second validity period of the target content is reached.
308. And when the contribution value trend of the target content is that the target content is currently in a prosperous period and the online time of the target content reaches the second validity period, prolonging the second validity period of the target content to be a third validity period.
When it is determined in step 306 that the target content is currently in the prosperous period, the server may determine the online time of the target content according to the current time and the online time of the target content, determine whether the online time of the target content reaches the second validity period, and if so, extend the second validity period of the target content, e.g., extend the second validity period to be the third validity period.
Steps 307 and 308 are two possible implementations of adjusting the second validity period of the target content according to the contribution value trend of the target content. After the original validity period of the target content is prolonged, determining the contribution value trend of the target content every second time period to know that the target content is currently in the prosperous period or in the low-vagal period for a long time, so that the target content can be timely expired when the target content is in the low-vagal period for a long time, and the validity period of the target content can be timely prolonged when the target content is currently in the prosperous period and reaches the validity period of the target content after the target content is prolonged.
After the second validity period of the target content is prolonged, the server may continue to dynamically adjust the second validity period of the target content in every other period of time, and the specific process is the same as steps 305 to 308, and will not be repeated.
It will be appreciated that steps 305 to 308 are optional steps, and if the contribution value trend of the target content determined in step 302 is that the target content is currently in the low-vage period for a long time, the server may perform step 303 without performing step 304 or steps 305 to 308.
According to the technical scheme provided by the embodiment of the application, according to the contribution value trend of the content (namely the value trend contributed by the platform, the life cycle trend of the content is obtained, whether the content is in a declining period or a prosperous period is identified, the effective period of the content is dynamically adjusted, the effective period which accords with the life cycle trend of the content is set for each content, the difference degree of the effective periods of the content with different values is pulled open, the effective period of the potential content is prolonged, the residual value is exerted for more time, the effective period of the content in the declining period is shortened, and exposure to other higher-quality content is saved.
In order to better understand the effects of the above technical solutions provided by the embodiments of the present application, the effects of the above technical solutions will be described below by taking the case that the validity period (first validity period) of the original content is 72h as an example.
For example, the content can be graphics and texts, and the graphics and texts are mainly 72 hours in validity period. By calculating the contribution value of the content over each hour of 72h, it is possible to analyze whether the content is in the low-vagal or declining phase over each hour of 72h, see several example cases shown in fig. 4-6:
Referring to fig. 4, fig. 4 is a schematic diagram of a latency period in the original validity period according to an embodiment of the present application, where the horizontal axis in fig. 4 is time t and the vertical axis is contribution value w. As shown in fig. 4, the content was in the 72h period with little success of cold start and was in the latency period, and such content accounted for 58%. For such cold start failed content, its expiration period may be determined to be immediately expired when 72 hours are reached.
Referring to fig. 5, fig. 5 is a schematic diagram of a decay period when an original validity period expires, where a horizontal axis in fig. 5 is time t and a vertical axis is contribution value w. As shown in fig. 5, the content was successfully cold started within 72h, and after the prosperous period, the decay period was entered, and then the prosperous period was not entered again for a long time, and the content was 22%. For such content that has entered the decay period very early before 72h is reached, the validity period should also be determined to expire immediately when 72h is reached.
Referring to fig. 6, fig. 6 is a schematic diagram of a prosperous period still when a predetermined validity period expires, and in fig. 6, the horizontal axis represents time t and the vertical axis represents contribution value w. As shown in fig. 6, the content was successful in 72 hours, and was periodically subjected to a "prosperous-decaying" process, which was still in the prosperous period at the expiration of the original validity period, such content being 20%. For such content, its validity period should be extended when 72h is reached.
In order to more intuitively show the contribution value trend of the content, a schematic stage division diagram is provided below, referring to fig. 7, fig. 7 is a schematic stage division diagram provided by the embodiment of the present application, where the horizontal axis in fig. 7 is time t, and the vertical axis is the contribution value w. The 20% score is marked as "inflection point Y", i.e., 80% of the time the content is considered to be in the prosperous phase and 20% of the time the content is considered to be in the low-vagal phase. As shown in fig. 7, if the content is in the latent period for a long time and the inflection point Y is not reached until the prosperity period, the validity period of the content is set to expire immediately. If the content enters the prosperous period after being rapidly cold started, the prosperous period is prolonged if the content still exists in the prosperous period when reaching the effective period. If the content is in the low-priced period after the prosperity period, if the long-time low prizing does not reach the inflection point Y again, the effective period of the content is set to be immediately expired, if the content is in the prosperity period again after the short-time low prizing period, the period continues, and the cycle is repeated.
Referring to fig. 8, fig. 8 is a schematic diagram of an effective period calculation provided by an embodiment of the present application, where "0" in fig. 8 indicates a low-vage period and "1" indicates a prosperity period, as shown in fig. 8 (a), if the content is still in the prosperity period, such as the last 1 in "00001111", when the effective period of the content is reached, the effective period of the content can be prolonged. If the content is in the low-vage period for a long time after the delay, such as the last four 0 s in "000011110000", the validity period of the content can be shortened to be immediately expired. If a short period of low-priced re-enters the prosperity period after the expiration of the content is extended, and then enters the decay period again, such as the last four 0 s in "00001111000011110000", the expiration of the content can be shortened to be immediately expired.
The technical scheme provided by the embodiment of the application dynamically adjusts (prolongs/shortens) the validity period of the content, and directly affects the size and structure of the content pool. The content in the low-prizing period for a long time is expired in advance, the content still in the prospering period when reaching the effective period is continued to prolong the effective period, the size and the structure of a content pool are optimized, and the recommending effect of the recommending side is indirectly influenced. For example:
(1) The size of the content pool is affected, for example, during holidays and weekends, the text distribution amount of a sender is reduced by 20% compared with that of a working day, but the number of visiting users is increased by 36% due to fake-free, the content is insufficient, but the users are exploded, so that the content is not required to be supplied, the validity period of the content is properly and dynamically prolonged, the magnitude of the content pool is increased, and the problem of recall shortage caused by user visiting is solved;
(2) The structure of the content pool is affected, for example, the classified storage amount of movies is 1 kilo per day, the classified storage amount of entertainment is 1 kilo per day, the average valid period of the content of the movie classification is 10 days, the average valid period of the entertainment classification is 1 day, and the storage amount is 1:10, but the valid period is different, so the content structure is 1:1.
In order to verify the effect of the technical scheme provided by the embodiment of the application, two groups of experiments are performed by using the technical scheme, one group is an experiment for dynamically prolonging the validity period, and the other group is an experiment for dynamically shortening the validity period. Referring to fig. 9 and 10, fig. 9 and 10 are schematic diagrams of experimental effects of dynamically prolonging the validity period provided by the embodiment of the present application, the experimental barrel and the comparison barrel in fig. 9 correspond to two groups of users respectively, different recommendation pools are adopted for the users of the experimental barrel and the users of the comparison barrel to recommend contents, an experimental index is an image-text (page view) index, fig. 9 shows relevant data of the index, lines with data mark points as dots in fig. 9 are data lines of the experimental barrel, lines with data mark points as triangles are data lines of the comparison barrel, the horizontal axes of the two data lines are time, the vertical axes are index values, and dotted lines in fig. 9 are time points for starting the experiment, that is, time points for prolonging the validity period. From the data of the two data lines in fig. 9, the relative difference of each group of data (data of the experimental barrel and the control barrel on the same day) can be calculated, the relative difference of each group of data= (experimental barrel data-control barrel data)/control barrel data, fig. 10 shows the data line of the relative difference of the experimental barrel and the control barrel, as can be seen from fig. 10, after the experiment is started (right side of the dotted line), the relative difference is always greater than 0, the greater than 0 indicates that the experiment achieves the positive effect, the greater the relative difference, the positive effect is more obvious, and the positive effect is achieved to indicate that the content recommended to the user is the content that the user is willing to view. According to the data of the two data lines in fig. 9, a correction difference ratio of the data average value may also be calculated, where the correction difference ratio= (experimental barrel data average value-control barrel data average value+correction value)/control barrel data average value, where the experimental barrel data average value is the average value of the experimental barrel data on the right side of the dotted line in fig. 9, and the control barrel data average value is the average value of the control barrel data on the right side of the dotted line in fig. 9, where the correction value may be greater than 0 or less than 0, and is used to correct the data deviation between the experimental barrel and the control barrel before the experiment starts (the experimental barrel data on the left side of the dotted line and the control barrel data should be consistent, but some deviation is found in the experiment), and the calculated correction difference ratio is 0.51%, greater than 0, which indicates that the experiment achieves the forward effect.
Referring to fig. 11 and fig. 12, fig. 11 and fig. 12 are schematic diagrams of experimental effects of dynamically shortening the validity period provided in the embodiments of the present application, the experimental barrel and the comparison barrel in fig. 11 correspond to two groups of users respectively, different recommendation pools are adopted for the users of the experimental barrel and the users of the comparison barrel to recommend contents, an experimental index is an image-text (page view) index, fig. 11 shows relevant data of the index, lines with data mark points as dots in fig. 11 are data lines of the experimental barrel, lines with data mark points as triangles are data lines of the comparison barrel, the horizontal axes of the two data lines are time, the vertical axes are index values, and a dotted line in fig. 11 is a time point of starting the experiment, that is, a time point of shortening the validity period. The relative difference of each group of data can be calculated according to the data of the two data lines in fig. 11, and the data lines of the relative difference between the experimental barrel and the control barrel are shown in fig. 12, and as can be seen from fig. 12, after the experiment is started (right side of the dotted line), the relative difference is always greater than 0, and the fact that the relative difference is greater than 0 indicates that the experiment achieves the positive effect. According to the data of the two data lines in fig. 9, the correction difference ratio of the data mean value can also be calculated, and the calculated correction difference ratio is 0.09%, and is larger than 0, which indicates that the experiment achieves the forward effect.
Both groups of experimental results show that the technical scheme is utilized to dynamically adjust the effective period of the content according to the contribution value trend (the value contributing to the large disc) of the content, so that the size and the structure of a content pool are dynamically adjusted, the recommendation side is provided with a forward effect, and the forward effect of the experiment for prolonging the effective period is obvious.
According to the method provided by the embodiment of the application, the contribution value of the content in the plurality of time periods is determined according to the feedback data of the content in the plurality of time periods of the original validity period, the content is not directly expired immediately when the original validity period is reached, but the validity period of the content is adjusted according to the trend of the contribution value, so that the flexibility of the validity period setting is improved, and the contribution value is determined according to the feedback data due to the fact that the validity period is adjusted.
Fig. 13 is a schematic structural diagram of a device for adjusting the validity period of content according to an embodiment of the present application. Referring to fig. 13, the apparatus includes:
An obtaining module 1301, configured to obtain contribution values of a target content in a plurality of first time periods according to feedback data of the target content in the plurality of first time periods included in a first validity period;
A determining module 1302, configured to determine a contribution value trend of the target content according to the contribution values of the target content in the plurality of first time periods when the online time length of the target content reaches the first validity period;
The adjusting module 1303 is configured to adjust the first validity period of the target content according to a contribution value trend of the target content.
In one possible implementation, the determining module 1302 is configured to:
obtaining percentiles of contribution values of the target content in the first time periods;
And when the contribution value of the target content in one first time period closest to the current time in the first time periods is larger than the percentile, determining that the contribution value trend of the target content is the current prosperity of the target content.
In one possible implementation, the determining module is configured to:
And when the contribution value of the target content in the target number of first time periods closest to the current time in the first time periods is smaller than or equal to the percentile, determining that the contribution value trend of the target content is that the target content is in the low-camouflage period for a long time.
In one possible implementation, the adjusting module 1303 is configured to:
And when the contribution value trend of the target content is that the target content is currently in a prosperous period, prolonging the first validity period of the target content to be a second validity period.
In one possible implementation, the adjusting module 1303 is configured to:
And when the contribution value trend of the target content is that the target content is currently in a low-camouflage period for a long time, determining that the first effective period of the target content is immediately expired.
In one possible implementation manner, the obtaining module 1301 is further configured to obtain, at intervals of a second time period, a contribution value of the target content in the second time period according to feedback data of the target content in the second time period;
The determining module 1302 is further configured to determine a contribution value trend of the target content according to the currently acquired contribution value of the target content and the historically acquired contribution value of the target content;
the adjusting module 1303 is further configured to adjust the second validity period of the target content according to a contribution value trend of the target content.
In one possible implementation, the determining module 1302 is configured to:
Obtaining a percentile of a plurality of contribution values of the target content, the plurality of contribution values including the currently obtained contribution value of the target content and the historically obtained contribution value of the target content;
And when the acquired target number of the plurality of contribution values, the time of which is closest to the current time, is smaller than or equal to the percentile, determining that the contribution value trend of the target content is that the target content is in the low-camouflage period for a long time.
In one possible implementation, the determining module 1302 is configured to:
And when the contribution value of the currently acquired target content is larger than the percentile, determining that the contribution value trend of the target content is that the target content is currently in a prosperity period.
In one possible implementation, the adjusting module 1303 is configured to:
and shortening the second effective period of the target content to be immediately expired when the contribution value trend of the target content is that the target content is currently in a low-camouflage period for a long time.
In one possible implementation, the adjusting module 1303 is configured to:
and when the contribution value trend of the target content is that the target content is currently in a prosperous period and the online time of the target content reaches the second effective period, prolonging the second effective period of the target content to be a third effective period.
It should be noted that: in the adjustment of the content validity period provided in the foregoing embodiment, only the division of the functional modules is used for illustration, and in practical application, the allocation of the functions may be performed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules, so as to complete all or part of the functions described above. In addition, the adjusting device for the content validity period provided in the above embodiment and the embodiment of the method for adjusting the content validity period belong to the same concept, and detailed implementation processes of the adjusting device and the embodiment of the method are detailed in the embodiment of the method, and are not repeated here.
Fig. 14 is a schematic structural diagram of a server 1400 according to an embodiment of the present application, where the server 1400 may have a relatively large difference due to different configurations or performances, and may include one or more processors (central processing units, CPUs) 1401 and one or more memories 1402, where at least one program code is stored in the memories 1402, and the at least one program code is loaded and executed by the processors 1401 to implement the methods provided in the above-mentioned method embodiments. Of course, the server may also have a wired or wireless network interface, a keyboard, an input/output interface, and other components for implementing the functions of the device, which are not described herein.
In an exemplary embodiment, there is also provided a computer readable storage medium storing at least one program code, for example, a memory storing at least one program code, which is loaded and executed by a processor to implement the content validity period adjustment method in the above embodiment. For example, the computer readable storage medium may be Read-Only Memory (ROM), random-access Memory (Random Access Memory, RAM), compact disk Read-Only Memory (CD-ROM), magnetic tape, floppy disk, optical data storage device, and the like.
It will be appreciated by those of ordinary skill in the art that all or part of the steps of implementing the above embodiments may be implemented by hardware, or may be implemented by hardware associated with program instructions, where the program may be stored on a computer readable storage medium, where the storage medium may be a read-only memory, a magnetic disk or optical disk, or the like.
The foregoing is illustrative of the present application and is not to be construed as limiting thereof, but rather as various modifications, equivalent arrangements, improvements, etc., which fall within the spirit and principles of the present application.
Claims (12)
1. A method for adjusting a validity period of content, the method comprising:
Acquiring the contribution value of target content in a plurality of first time periods according to feedback data of the target content in the first time periods; the contribution value refers to the value of the target content contributing to the platform;
When the online time of the target content reaches the first effective period, determining a contribution value trend of the target content according to the contribution values of the target content in the plurality of first time periods;
according to the contribution value trend of the target content, the first validity period of the target content is adjusted;
The determining a contribution value trend of the target content according to the contribution values of the target content in the first time periods comprises the following steps:
sequencing the contribution values of the target content in the plurality of first time periods from small to large, and acquiring percentiles of the contribution values of the target content in the plurality of first time periods;
When the contribution value of the target content in one first time period closest to the current time in the first time periods is larger than the percentile, determining that the contribution value trend of the target content is the current prosperity of the target content;
And when the contribution value of the target content in the target number of first time periods closest to the current time in the first time periods is smaller than or equal to the percentile, determining that the contribution value trend of the target content is that the target content is in the low-camouflage period for a long time.
2. The method of claim 1, wherein adjusting the first validity period of the target content according to the contribution value trend of the target content comprises:
And when the contribution value trend of the target content is that the target content is currently in a prosperous period, prolonging the first validity period of the target content to be a second validity period.
3. The method of claim 2, wherein after the extending the first validity period of the target content to a second validity period, the method further comprises:
acquiring the contribution value of the target content in a second time period according to the feedback data of the target content in the second time period every second time period;
Determining a contribution value trend of the target content according to the currently acquired contribution value of the target content and the historically acquired contribution value of the target content;
And adjusting the second validity period of the target content according to the contribution value trend of the target content.
4. A method according to claim 3, wherein said adjusting said second validity period of said target content according to a contribution value trend of said target content comprises:
and shortening the second effective period of the target content to be immediately expired when the contribution value trend of the target content is that the target content is currently in a low-camouflage period for a long time.
5. A method according to claim 3, wherein said adjusting said second validity period of said target content according to a contribution value trend of said target content comprises:
and when the contribution value trend of the target content is that the target content is currently in a prosperous period and the online time of the target content reaches the second effective period, prolonging the second effective period of the target content to be a third effective period.
6. An apparatus for adjusting a content expiration date, the apparatus comprising:
The acquisition module is used for acquiring the contribution value of the target content in a plurality of first time periods according to the feedback data of the target content in the first time periods; the contribution value refers to the value of the target content contributing to the platform;
the determining module is used for determining a contribution value trend of the target content according to the contribution values of the target content in the plurality of first time periods when the online time length of the target content reaches the first effective period;
the adjustment module is used for adjusting the first validity period of the target content according to the contribution value trend of the target content;
The determining module is used for:
sequencing the contribution values of the target content in the plurality of first time periods from small to large, and acquiring percentiles of the contribution values of the target content in the plurality of first time periods;
When the contribution value of the target content in one first time period closest to the current time in the first time periods is larger than the percentile, determining that the contribution value trend of the target content is the current prosperity of the target content;
And when the contribution value of the target content in the target number of first time periods closest to the current time in the first time periods is smaller than or equal to the percentile, determining that the contribution value trend of the target content is that the target content is in the low-camouflage period for a long time.
7. The apparatus of claim 6, wherein the adjustment module is to:
And when the contribution value trend of the target content is that the target content is currently in a prosperous period, prolonging the first validity period of the target content to be a second validity period.
8. The apparatus of claim 7, wherein the obtaining module is further configured to obtain, at every second time period, a contribution value of the target content in the second time period according to feedback data of the target content in the second time period;
the determining module is further used for determining a contribution value trend of the target content according to the currently acquired contribution value of the target content and the historically acquired contribution value of the target content;
the adjustment module is further configured to adjust the second validity period of the target content according to a contribution value trend of the target content.
9. The apparatus of claim 8, the adjustment module to:
and shortening the second effective period of the target content to be immediately expired when the contribution value trend of the target content is that the target content is currently in a low-camouflage period for a long time.
10. The apparatus of claim 8, the adjustment module to:
and when the contribution value trend of the target content is that the target content is currently in a prosperous period and the online time of the target content reaches the second effective period, prolonging the second effective period of the target content to be a third effective period.
11. A server comprising a processor and a memory, wherein the memory has stored therein at least one piece of program code that is loaded and executed by the processor to implement the method of adjusting the validity period of content according to any one of claims 1 to 5.
12. A computer readable storage medium, wherein at least one program code is stored in the computer readable storage medium, the at least one program code being loaded and executed by a processor to implement the method of adjusting a content validity period according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911312413.2A CN113010817B (en) | 2019-12-18 | 2019-12-18 | Content validity period adjusting method, device, server and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911312413.2A CN113010817B (en) | 2019-12-18 | 2019-12-18 | Content validity period adjusting method, device, server and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113010817A CN113010817A (en) | 2021-06-22 |
| CN113010817B true CN113010817B (en) | 2024-05-10 |
Family
ID=76382464
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911312413.2A Active CN113010817B (en) | 2019-12-18 | 2019-12-18 | Content validity period adjusting method, device, server and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113010817B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2571026A2 (en) * | 2011-09-15 | 2013-03-20 | Sony Corporation | Information processing apparatus, information processing method and program |
| JP2013065089A (en) * | 2011-09-15 | 2013-04-11 | Sony Corp | Information processing apparatus, information processing method, and program |
| CN103260062A (en) * | 2012-02-15 | 2013-08-21 | 深圳市腾讯计算机系统有限公司 | Method and device for carrying out content play and control over client sides |
| CN106484671A (en) * | 2015-08-25 | 2017-03-08 | 北京中搜网络技术股份有限公司 | A kind of recognition methodss of ageing inquiry content |
-
2019
- 2019-12-18 CN CN201911312413.2A patent/CN113010817B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2571026A2 (en) * | 2011-09-15 | 2013-03-20 | Sony Corporation | Information processing apparatus, information processing method and program |
| JP2013065089A (en) * | 2011-09-15 | 2013-04-11 | Sony Corp | Information processing apparatus, information processing method, and program |
| CN103260062A (en) * | 2012-02-15 | 2013-08-21 | 深圳市腾讯计算机系统有限公司 | Method and device for carrying out content play and control over client sides |
| CN106484671A (en) * | 2015-08-25 | 2017-03-08 | 北京中搜网络技术股份有限公司 | A kind of recognition methodss of ageing inquiry content |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113010817A (en) | 2021-06-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8214492B2 (en) | Method and system for adapting a session timeout period | |
| EP3355210A1 (en) | Media file release method and apparatus | |
| CN112016773B (en) | Method and device for determining potential anchor | |
| CN113015010B (en) | Push parameter determination method, device, equipment and computer readable storage medium | |
| CN111031336A (en) | Live broadcast list data updating method and device, electronic equipment and storage medium | |
| CN109274987A (en) | A kind of video collection sort method, server and readable storage medium storing program for executing | |
| CN111651666A (en) | User theme recommendation method and device, computer equipment and storage medium | |
| CN113382289B (en) | Live broadcast room delivery method and device, electronic equipment and storage medium | |
| CN113139826A (en) | Method and device for determining distribution authority of advertisement space and computer equipment | |
| CN112423134A (en) | Video content recommendation method and device and computer equipment | |
| CN113010817B (en) | Content validity period adjusting method, device, server and storage medium | |
| CN111475678B (en) | Method, server and terminal for pushing search results | |
| CN113222720A (en) | Reputation-based privacy protection incentive mechanism method, device and storage medium | |
| CN115375339A (en) | Multimedia information recommendation method, device and equipment and computer storage medium | |
| CN114553786B (en) | Network request fusing method and device, computer equipment and storage medium | |
| CN110933504A (en) | Video recommendation method, device, server and storage medium | |
| JP5169173B2 (en) | Information distribution system, information distribution method, and information distribution program | |
| CN114201696A (en) | Message pushing method and device, storage medium and computer equipment | |
| CN113596597A (en) | Game video acceleration method and device, computer equipment and storage medium | |
| CN114386999A (en) | Media file delivery method and device | |
| KR20130054690A (en) | Method and apparatus for providing advertisement | |
| CN111666486A (en) | Heat value acquisition method and device | |
| CN112073454A (en) | Resource distribution method and device and electronic equipment | |
| CN115203577B (en) | Object recommendation method, and training method and device of object recommendation model | |
| CN110674412A (en) | Resource recommendation information pushing method and device and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 40050119 Country of ref document: HK |
|
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20221121 Address after: 1402, Floor 14, Block A, Haina Baichuan Headquarters Building, No. 6, Baoxing Road, Haibin Community, Xin'an Street, Bao'an District, Shenzhen, Guangdong 518133 Applicant after: Shenzhen Yayue Technology Co.,Ltd. Address before: 518057 Tencent Building, No. 1 High-tech Zone, Nanshan District, Shenzhen City, Guangdong Province, 35 floors Applicant before: TENCENT TECHNOLOGY (SHENZHEN) Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |